Instructions to use aee4/G17-AMFU-Net with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aee4/G17-AMFU-Net with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AMFUNet model = AMFUNet.from_pretrained("aee4/G17-AMFU-Net", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 9000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 24995616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fd5b4ae808fdb2752f49379ad06420f8f5a81937496f0ed1d1a900e3a856909
|
| 3 |
size 24995616
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 49993547
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de0464ac57aa359b6eb57b5a1e897f169f45ce3a1bcea3940fe5021434e98bed
|
| 3 |
size 49993547
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ee34062530866a754b7d215e3569f051455e042c0dd4cfdd40d63ebd3a659e8
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:631f01a8f155f83975aa0c5b53bc0eb0a8787a37646c3816c93a7c0986ab01d0
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 250,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2916,501 +2916,86 @@
|
|
| 2916 |
},
|
| 2917 |
{
|
| 2918 |
"epoch": 41.58767772511848,
|
| 2919 |
-
"grad_norm": 1.
|
| 2920 |
"learning_rate": 9.208530805687204e-05,
|
| 2921 |
-
"loss": 0.
|
| 2922 |
"step": 8775
|
| 2923 |
},
|
| 2924 |
{
|
| 2925 |
"epoch": 41.70616113744076,
|
| 2926 |
-
"grad_norm":
|
| 2927 |
"learning_rate": 9.149289099526066e-05,
|
| 2928 |
-
"loss": 0.
|
| 2929 |
"step": 8800
|
| 2930 |
},
|
| 2931 |
{
|
| 2932 |
"epoch": 41.824644549763036,
|
| 2933 |
-
"grad_norm": 1.
|
| 2934 |
"learning_rate": 9.090047393364928e-05,
|
| 2935 |
-
"loss": 0.
|
| 2936 |
"step": 8825
|
| 2937 |
},
|
| 2938 |
{
|
| 2939 |
"epoch": 41.943127962085306,
|
| 2940 |
-
"grad_norm": 0.
|
| 2941 |
"learning_rate": 9.03080568720379e-05,
|
| 2942 |
-
"loss": 0.
|
| 2943 |
"step": 8850
|
| 2944 |
},
|
| 2945 |
{
|
| 2946 |
"epoch": 42.06161137440758,
|
| 2947 |
-
"grad_norm":
|
| 2948 |
"learning_rate": 8.971563981042653e-05,
|
| 2949 |
-
"loss": 0.
|
| 2950 |
"step": 8875
|
| 2951 |
},
|
| 2952 |
{
|
| 2953 |
"epoch": 42.18009478672986,
|
| 2954 |
-
"grad_norm":
|
| 2955 |
"learning_rate": 8.912322274881517e-05,
|
| 2956 |
-
"loss": 0.
|
| 2957 |
"step": 8900
|
| 2958 |
},
|
| 2959 |
{
|
| 2960 |
"epoch": 42.29857819905213,
|
| 2961 |
-
"grad_norm":
|
| 2962 |
"learning_rate": 8.853080568720378e-05,
|
| 2963 |
-
"loss": 0.
|
| 2964 |
"step": 8925
|
| 2965 |
},
|
| 2966 |
{
|
| 2967 |
"epoch": 42.41706161137441,
|
| 2968 |
-
"grad_norm": 0.
|
| 2969 |
"learning_rate": 8.793838862559241e-05,
|
| 2970 |
-
"loss": 0.
|
| 2971 |
"step": 8950
|
| 2972 |
},
|
| 2973 |
{
|
| 2974 |
"epoch": 42.535545023696685,
|
| 2975 |
-
"grad_norm":
|
| 2976 |
"learning_rate": 8.734597156398103e-05,
|
| 2977 |
-
"loss": 0.
|
| 2978 |
"step": 8975
|
| 2979 |
},
|
| 2980 |
{
|
| 2981 |
"epoch": 42.654028436018955,
|
| 2982 |
-
"grad_norm":
|
| 2983 |
"learning_rate": 8.675355450236965e-05,
|
| 2984 |
-
"loss": 0.
|
| 2985 |
"step": 9000
|
| 2986 |
},
|
| 2987 |
{
|
| 2988 |
"epoch": 42.654028436018955,
|
| 2989 |
-
"eval_dice": 0.
|
| 2990 |
-
"eval_iou": 0.
|
| 2991 |
-
"eval_loss": 0.
|
| 2992 |
-
"eval_precision": 0.
|
| 2993 |
-
"eval_recall": 0.
|
| 2994 |
-
"eval_runtime":
|
| 2995 |
-
"eval_samples_per_second":
|
| 2996 |
-
"eval_specificity": 0.
|
| 2997 |
-
"eval_steps_per_second": 26.
|
| 2998 |
"step": 9000
|
| 2999 |
-
},
|
| 3000 |
-
{
|
| 3001 |
-
"epoch": 42.77251184834123,
|
| 3002 |
-
"grad_norm": 0.797553300857544,
|
| 3003 |
-
"learning_rate": 8.61611374407583e-05,
|
| 3004 |
-
"loss": 0.2693,
|
| 3005 |
-
"step": 9025
|
| 3006 |
-
},
|
| 3007 |
-
{
|
| 3008 |
-
"epoch": 42.89099526066351,
|
| 3009 |
-
"grad_norm": 1.7162684202194214,
|
| 3010 |
-
"learning_rate": 8.556872037914691e-05,
|
| 3011 |
-
"loss": 0.2528,
|
| 3012 |
-
"step": 9050
|
| 3013 |
-
},
|
| 3014 |
-
{
|
| 3015 |
-
"epoch": 43.00947867298578,
|
| 3016 |
-
"grad_norm": 1.0431219339370728,
|
| 3017 |
-
"learning_rate": 8.497630331753554e-05,
|
| 3018 |
-
"loss": 0.2284,
|
| 3019 |
-
"step": 9075
|
| 3020 |
-
},
|
| 3021 |
-
{
|
| 3022 |
-
"epoch": 43.127962085308056,
|
| 3023 |
-
"grad_norm": 1.6838188171386719,
|
| 3024 |
-
"learning_rate": 8.438388625592417e-05,
|
| 3025 |
-
"loss": 0.2364,
|
| 3026 |
-
"step": 9100
|
| 3027 |
-
},
|
| 3028 |
-
{
|
| 3029 |
-
"epoch": 43.24644549763033,
|
| 3030 |
-
"grad_norm": 0.7753061652183533,
|
| 3031 |
-
"learning_rate": 8.379146919431278e-05,
|
| 3032 |
-
"loss": 0.2114,
|
| 3033 |
-
"step": 9125
|
| 3034 |
-
},
|
| 3035 |
-
{
|
| 3036 |
-
"epoch": 43.36492890995261,
|
| 3037 |
-
"grad_norm": 4.212740421295166,
|
| 3038 |
-
"learning_rate": 8.319905213270142e-05,
|
| 3039 |
-
"loss": 0.2753,
|
| 3040 |
-
"step": 9150
|
| 3041 |
-
},
|
| 3042 |
-
{
|
| 3043 |
-
"epoch": 43.48341232227488,
|
| 3044 |
-
"grad_norm": 11.296808242797852,
|
| 3045 |
-
"learning_rate": 8.260663507109004e-05,
|
| 3046 |
-
"loss": 0.2446,
|
| 3047 |
-
"step": 9175
|
| 3048 |
-
},
|
| 3049 |
-
{
|
| 3050 |
-
"epoch": 43.60189573459716,
|
| 3051 |
-
"grad_norm": 3.462747812271118,
|
| 3052 |
-
"learning_rate": 8.201421800947867e-05,
|
| 3053 |
-
"loss": 0.2478,
|
| 3054 |
-
"step": 9200
|
| 3055 |
-
},
|
| 3056 |
-
{
|
| 3057 |
-
"epoch": 43.720379146919434,
|
| 3058 |
-
"grad_norm": 9.75444221496582,
|
| 3059 |
-
"learning_rate": 8.14218009478673e-05,
|
| 3060 |
-
"loss": 0.2263,
|
| 3061 |
-
"step": 9225
|
| 3062 |
-
},
|
| 3063 |
-
{
|
| 3064 |
-
"epoch": 43.838862559241704,
|
| 3065 |
-
"grad_norm": 0.530179500579834,
|
| 3066 |
-
"learning_rate": 8.082938388625591e-05,
|
| 3067 |
-
"loss": 0.2486,
|
| 3068 |
-
"step": 9250
|
| 3069 |
-
},
|
| 3070 |
-
{
|
| 3071 |
-
"epoch": 43.838862559241704,
|
| 3072 |
-
"eval_dice": 0.838824375147426,
|
| 3073 |
-
"eval_iou": 0.7557838543476992,
|
| 3074 |
-
"eval_loss": 0.2860996425151825,
|
| 3075 |
-
"eval_precision": 0.8766696737064822,
|
| 3076 |
-
"eval_recall": 0.8393992955724784,
|
| 3077 |
-
"eval_runtime": 4.0687,
|
| 3078 |
-
"eval_samples_per_second": 103.226,
|
| 3079 |
-
"eval_specificity": 0.9885572710533146,
|
| 3080 |
-
"eval_steps_per_second": 25.807,
|
| 3081 |
-
"step": 9250
|
| 3082 |
-
},
|
| 3083 |
-
{
|
| 3084 |
-
"epoch": 43.95734597156398,
|
| 3085 |
-
"grad_norm": 9.763873100280762,
|
| 3086 |
-
"learning_rate": 8.023696682464455e-05,
|
| 3087 |
-
"loss": 0.2747,
|
| 3088 |
-
"step": 9275
|
| 3089 |
-
},
|
| 3090 |
-
{
|
| 3091 |
-
"epoch": 44.07582938388626,
|
| 3092 |
-
"grad_norm": 3.262601613998413,
|
| 3093 |
-
"learning_rate": 7.964454976303318e-05,
|
| 3094 |
-
"loss": 0.2598,
|
| 3095 |
-
"step": 9300
|
| 3096 |
-
},
|
| 3097 |
-
{
|
| 3098 |
-
"epoch": 44.19431279620853,
|
| 3099 |
-
"grad_norm": 3.508969306945801,
|
| 3100 |
-
"learning_rate": 7.905213270142179e-05,
|
| 3101 |
-
"loss": 0.2223,
|
| 3102 |
-
"step": 9325
|
| 3103 |
-
},
|
| 3104 |
-
{
|
| 3105 |
-
"epoch": 44.312796208530806,
|
| 3106 |
-
"grad_norm": 8.580510139465332,
|
| 3107 |
-
"learning_rate": 7.845971563981042e-05,
|
| 3108 |
-
"loss": 0.2447,
|
| 3109 |
-
"step": 9350
|
| 3110 |
-
},
|
| 3111 |
-
{
|
| 3112 |
-
"epoch": 44.43127962085308,
|
| 3113 |
-
"grad_norm": 2.567824602127075,
|
| 3114 |
-
"learning_rate": 7.786729857819904e-05,
|
| 3115 |
-
"loss": 0.2324,
|
| 3116 |
-
"step": 9375
|
| 3117 |
-
},
|
| 3118 |
-
{
|
| 3119 |
-
"epoch": 44.54976303317535,
|
| 3120 |
-
"grad_norm": 9.435370445251465,
|
| 3121 |
-
"learning_rate": 7.727488151658768e-05,
|
| 3122 |
-
"loss": 0.2814,
|
| 3123 |
-
"step": 9400
|
| 3124 |
-
},
|
| 3125 |
-
{
|
| 3126 |
-
"epoch": 44.66824644549763,
|
| 3127 |
-
"grad_norm": 1.7678611278533936,
|
| 3128 |
-
"learning_rate": 7.66824644549763e-05,
|
| 3129 |
-
"loss": 0.2475,
|
| 3130 |
-
"step": 9425
|
| 3131 |
-
},
|
| 3132 |
-
{
|
| 3133 |
-
"epoch": 44.78672985781991,
|
| 3134 |
-
"grad_norm": 4.226409912109375,
|
| 3135 |
-
"learning_rate": 7.609004739336492e-05,
|
| 3136 |
-
"loss": 0.2304,
|
| 3137 |
-
"step": 9450
|
| 3138 |
-
},
|
| 3139 |
-
{
|
| 3140 |
-
"epoch": 44.90521327014218,
|
| 3141 |
-
"grad_norm": 1.0879155397415161,
|
| 3142 |
-
"learning_rate": 7.549763033175355e-05,
|
| 3143 |
-
"loss": 0.2441,
|
| 3144 |
-
"step": 9475
|
| 3145 |
-
},
|
| 3146 |
-
{
|
| 3147 |
-
"epoch": 45.023696682464454,
|
| 3148 |
-
"grad_norm": 1.1447354555130005,
|
| 3149 |
-
"learning_rate": 7.490521327014218e-05,
|
| 3150 |
-
"loss": 0.2572,
|
| 3151 |
-
"step": 9500
|
| 3152 |
-
},
|
| 3153 |
-
{
|
| 3154 |
-
"epoch": 45.023696682464454,
|
| 3155 |
-
"eval_dice": 0.8321944502718175,
|
| 3156 |
-
"eval_iou": 0.7514988390519137,
|
| 3157 |
-
"eval_loss": 0.2912711501121521,
|
| 3158 |
-
"eval_precision": 0.8604860473540565,
|
| 3159 |
-
"eval_recall": 0.857015643980932,
|
| 3160 |
-
"eval_runtime": 4.0029,
|
| 3161 |
-
"eval_samples_per_second": 104.923,
|
| 3162 |
-
"eval_specificity": 0.9863909301122319,
|
| 3163 |
-
"eval_steps_per_second": 26.231,
|
| 3164 |
-
"step": 9500
|
| 3165 |
-
},
|
| 3166 |
-
{
|
| 3167 |
-
"epoch": 45.14218009478673,
|
| 3168 |
-
"grad_norm": 1.5708271265029907,
|
| 3169 |
-
"learning_rate": 7.43127962085308e-05,
|
| 3170 |
-
"loss": 0.2246,
|
| 3171 |
-
"step": 9525
|
| 3172 |
-
},
|
| 3173 |
-
{
|
| 3174 |
-
"epoch": 45.26066350710901,
|
| 3175 |
-
"grad_norm": 2.45312762260437,
|
| 3176 |
-
"learning_rate": 7.372037914691943e-05,
|
| 3177 |
-
"loss": 0.2616,
|
| 3178 |
-
"step": 9550
|
| 3179 |
-
},
|
| 3180 |
-
{
|
| 3181 |
-
"epoch": 45.37914691943128,
|
| 3182 |
-
"grad_norm": 2.3740899562835693,
|
| 3183 |
-
"learning_rate": 7.312796208530805e-05,
|
| 3184 |
-
"loss": 0.2255,
|
| 3185 |
-
"step": 9575
|
| 3186 |
-
},
|
| 3187 |
-
{
|
| 3188 |
-
"epoch": 45.497630331753555,
|
| 3189 |
-
"grad_norm": 2.8741822242736816,
|
| 3190 |
-
"learning_rate": 7.253554502369668e-05,
|
| 3191 |
-
"loss": 0.2531,
|
| 3192 |
-
"step": 9600
|
| 3193 |
-
},
|
| 3194 |
-
{
|
| 3195 |
-
"epoch": 45.61611374407583,
|
| 3196 |
-
"grad_norm": 6.013194561004639,
|
| 3197 |
-
"learning_rate": 7.19431279620853e-05,
|
| 3198 |
-
"loss": 0.2757,
|
| 3199 |
-
"step": 9625
|
| 3200 |
-
},
|
| 3201 |
-
{
|
| 3202 |
-
"epoch": 45.7345971563981,
|
| 3203 |
-
"grad_norm": 4.674959182739258,
|
| 3204 |
-
"learning_rate": 7.135071090047393e-05,
|
| 3205 |
-
"loss": 0.2226,
|
| 3206 |
-
"step": 9650
|
| 3207 |
-
},
|
| 3208 |
-
{
|
| 3209 |
-
"epoch": 45.85308056872038,
|
| 3210 |
-
"grad_norm": 0.952613890171051,
|
| 3211 |
-
"learning_rate": 7.075829383886256e-05,
|
| 3212 |
-
"loss": 0.2408,
|
| 3213 |
-
"step": 9675
|
| 3214 |
-
},
|
| 3215 |
-
{
|
| 3216 |
-
"epoch": 45.97156398104266,
|
| 3217 |
-
"grad_norm": 2.0920588970184326,
|
| 3218 |
-
"learning_rate": 7.016587677725117e-05,
|
| 3219 |
-
"loss": 0.2387,
|
| 3220 |
-
"step": 9700
|
| 3221 |
-
},
|
| 3222 |
-
{
|
| 3223 |
-
"epoch": 46.09004739336493,
|
| 3224 |
-
"grad_norm": 1.0705209970474243,
|
| 3225 |
-
"learning_rate": 6.95734597156398e-05,
|
| 3226 |
-
"loss": 0.2245,
|
| 3227 |
-
"step": 9725
|
| 3228 |
-
},
|
| 3229 |
-
{
|
| 3230 |
-
"epoch": 46.208530805687204,
|
| 3231 |
-
"grad_norm": 2.047121047973633,
|
| 3232 |
-
"learning_rate": 6.898104265402843e-05,
|
| 3233 |
-
"loss": 0.2257,
|
| 3234 |
-
"step": 9750
|
| 3235 |
-
},
|
| 3236 |
-
{
|
| 3237 |
-
"epoch": 46.208530805687204,
|
| 3238 |
-
"eval_dice": 0.8383902995071846,
|
| 3239 |
-
"eval_iou": 0.7569419008521788,
|
| 3240 |
-
"eval_loss": 0.2846696078777313,
|
| 3241 |
-
"eval_precision": 0.8555689538210236,
|
| 3242 |
-
"eval_recall": 0.8575600572033153,
|
| 3243 |
-
"eval_runtime": 4.0,
|
| 3244 |
-
"eval_samples_per_second": 105.0,
|
| 3245 |
-
"eval_specificity": 0.9855094003578792,
|
| 3246 |
-
"eval_steps_per_second": 26.25,
|
| 3247 |
-
"step": 9750
|
| 3248 |
-
},
|
| 3249 |
-
{
|
| 3250 |
-
"epoch": 46.32701421800948,
|
| 3251 |
-
"grad_norm": 1.6559125185012817,
|
| 3252 |
-
"learning_rate": 6.838862559241706e-05,
|
| 3253 |
-
"loss": 0.2237,
|
| 3254 |
-
"step": 9775
|
| 3255 |
-
},
|
| 3256 |
-
{
|
| 3257 |
-
"epoch": 46.44549763033175,
|
| 3258 |
-
"grad_norm": 1.5927103757858276,
|
| 3259 |
-
"learning_rate": 6.779620853080569e-05,
|
| 3260 |
-
"loss": 0.2192,
|
| 3261 |
-
"step": 9800
|
| 3262 |
-
},
|
| 3263 |
-
{
|
| 3264 |
-
"epoch": 46.56398104265403,
|
| 3265 |
-
"grad_norm": 9.687053680419922,
|
| 3266 |
-
"learning_rate": 6.72037914691943e-05,
|
| 3267 |
-
"loss": 0.2472,
|
| 3268 |
-
"step": 9825
|
| 3269 |
-
},
|
| 3270 |
-
{
|
| 3271 |
-
"epoch": 46.682464454976305,
|
| 3272 |
-
"grad_norm": 2.2457642555236816,
|
| 3273 |
-
"learning_rate": 6.661137440758293e-05,
|
| 3274 |
-
"loss": 0.255,
|
| 3275 |
-
"step": 9850
|
| 3276 |
-
},
|
| 3277 |
-
{
|
| 3278 |
-
"epoch": 46.800947867298575,
|
| 3279 |
-
"grad_norm": 10.048160552978516,
|
| 3280 |
-
"learning_rate": 6.601895734597156e-05,
|
| 3281 |
-
"loss": 0.2149,
|
| 3282 |
-
"step": 9875
|
| 3283 |
-
},
|
| 3284 |
-
{
|
| 3285 |
-
"epoch": 46.91943127962085,
|
| 3286 |
-
"grad_norm": 1.5694763660430908,
|
| 3287 |
-
"learning_rate": 6.542654028436019e-05,
|
| 3288 |
-
"loss": 0.2838,
|
| 3289 |
-
"step": 9900
|
| 3290 |
-
},
|
| 3291 |
-
{
|
| 3292 |
-
"epoch": 47.03791469194313,
|
| 3293 |
-
"grad_norm": 2.075925827026367,
|
| 3294 |
-
"learning_rate": 6.483412322274881e-05,
|
| 3295 |
-
"loss": 0.2328,
|
| 3296 |
-
"step": 9925
|
| 3297 |
-
},
|
| 3298 |
-
{
|
| 3299 |
-
"epoch": 47.156398104265406,
|
| 3300 |
-
"grad_norm": 3.465050220489502,
|
| 3301 |
-
"learning_rate": 6.424170616113743e-05,
|
| 3302 |
-
"loss": 0.2223,
|
| 3303 |
-
"step": 9950
|
| 3304 |
-
},
|
| 3305 |
-
{
|
| 3306 |
-
"epoch": 47.274881516587676,
|
| 3307 |
-
"grad_norm": 0.4745011627674103,
|
| 3308 |
-
"learning_rate": 6.364928909952606e-05,
|
| 3309 |
-
"loss": 0.1925,
|
| 3310 |
-
"step": 9975
|
| 3311 |
-
},
|
| 3312 |
-
{
|
| 3313 |
-
"epoch": 47.39336492890995,
|
| 3314 |
-
"grad_norm": 1.6556150913238525,
|
| 3315 |
-
"learning_rate": 6.305687203791468e-05,
|
| 3316 |
-
"loss": 0.243,
|
| 3317 |
-
"step": 10000
|
| 3318 |
-
},
|
| 3319 |
-
{
|
| 3320 |
-
"epoch": 47.39336492890995,
|
| 3321 |
-
"eval_dice": 0.8403776925789292,
|
| 3322 |
-
"eval_iou": 0.7570883607364053,
|
| 3323 |
-
"eval_loss": 0.28017136454582214,
|
| 3324 |
-
"eval_precision": 0.8452902582706101,
|
| 3325 |
-
"eval_recall": 0.8726460354149849,
|
| 3326 |
-
"eval_runtime": 4.0217,
|
| 3327 |
-
"eval_samples_per_second": 104.434,
|
| 3328 |
-
"eval_specificity": 0.9828701914870307,
|
| 3329 |
-
"eval_steps_per_second": 26.108,
|
| 3330 |
-
"step": 10000
|
| 3331 |
-
},
|
| 3332 |
-
{
|
| 3333 |
-
"epoch": 47.51184834123223,
|
| 3334 |
-
"grad_norm": 3.944502830505371,
|
| 3335 |
-
"learning_rate": 6.246445497630331e-05,
|
| 3336 |
-
"loss": 0.2098,
|
| 3337 |
-
"step": 10025
|
| 3338 |
-
},
|
| 3339 |
-
{
|
| 3340 |
-
"epoch": 47.6303317535545,
|
| 3341 |
-
"grad_norm": 1.6057257652282715,
|
| 3342 |
-
"learning_rate": 6.187203791469194e-05,
|
| 3343 |
-
"loss": 0.2423,
|
| 3344 |
-
"step": 10050
|
| 3345 |
-
},
|
| 3346 |
-
{
|
| 3347 |
-
"epoch": 47.74881516587678,
|
| 3348 |
-
"grad_norm": 5.08576774597168,
|
| 3349 |
-
"learning_rate": 6.127962085308057e-05,
|
| 3350 |
-
"loss": 0.2812,
|
| 3351 |
-
"step": 10075
|
| 3352 |
-
},
|
| 3353 |
-
{
|
| 3354 |
-
"epoch": 47.867298578199055,
|
| 3355 |
-
"grad_norm": 1.5568195581436157,
|
| 3356 |
-
"learning_rate": 6.0687203791469184e-05,
|
| 3357 |
-
"loss": 0.2452,
|
| 3358 |
-
"step": 10100
|
| 3359 |
-
},
|
| 3360 |
-
{
|
| 3361 |
-
"epoch": 47.985781990521325,
|
| 3362 |
-
"grad_norm": 1.5616092681884766,
|
| 3363 |
-
"learning_rate": 6.009478672985782e-05,
|
| 3364 |
-
"loss": 0.2199,
|
| 3365 |
-
"step": 10125
|
| 3366 |
-
},
|
| 3367 |
-
{
|
| 3368 |
-
"epoch": 48.1042654028436,
|
| 3369 |
-
"grad_norm": 1.298160433769226,
|
| 3370 |
-
"learning_rate": 5.950236966824644e-05,
|
| 3371 |
-
"loss": 0.2279,
|
| 3372 |
-
"step": 10150
|
| 3373 |
-
},
|
| 3374 |
-
{
|
| 3375 |
-
"epoch": 48.22274881516588,
|
| 3376 |
-
"grad_norm": 1.4128798246383667,
|
| 3377 |
-
"learning_rate": 5.890995260663507e-05,
|
| 3378 |
-
"loss": 0.2401,
|
| 3379 |
-
"step": 10175
|
| 3380 |
-
},
|
| 3381 |
-
{
|
| 3382 |
-
"epoch": 48.34123222748815,
|
| 3383 |
-
"grad_norm": 3.664189338684082,
|
| 3384 |
-
"learning_rate": 5.831753554502369e-05,
|
| 3385 |
-
"loss": 0.2571,
|
| 3386 |
-
"step": 10200
|
| 3387 |
-
},
|
| 3388 |
-
{
|
| 3389 |
-
"epoch": 48.459715639810426,
|
| 3390 |
-
"grad_norm": 1.5395433902740479,
|
| 3391 |
-
"learning_rate": 5.772511848341231e-05,
|
| 3392 |
-
"loss": 0.2176,
|
| 3393 |
-
"step": 10225
|
| 3394 |
-
},
|
| 3395 |
-
{
|
| 3396 |
-
"epoch": 48.5781990521327,
|
| 3397 |
-
"grad_norm": 0.6564604043960571,
|
| 3398 |
-
"learning_rate": 5.7132701421800946e-05,
|
| 3399 |
-
"loss": 0.2248,
|
| 3400 |
-
"step": 10250
|
| 3401 |
-
},
|
| 3402 |
-
{
|
| 3403 |
-
"epoch": 48.5781990521327,
|
| 3404 |
-
"eval_dice": 0.8362172984011872,
|
| 3405 |
-
"eval_iou": 0.7532469173349392,
|
| 3406 |
-
"eval_loss": 0.27925926446914673,
|
| 3407 |
-
"eval_precision": 0.8612305662284476,
|
| 3408 |
-
"eval_recall": 0.8482660596049372,
|
| 3409 |
-
"eval_runtime": 4.0119,
|
| 3410 |
-
"eval_samples_per_second": 104.69,
|
| 3411 |
-
"eval_specificity": 0.9858453922646354,
|
| 3412 |
-
"eval_steps_per_second": 26.172,
|
| 3413 |
-
"step": 10250
|
| 3414 |
}
|
| 3415 |
],
|
| 3416 |
"logging_steps": 25,
|
|
@@ -3425,7 +3010,7 @@
|
|
| 3425 |
"early_stopping_threshold": 0.0
|
| 3426 |
},
|
| 3427 |
"attributes": {
|
| 3428 |
-
"early_stopping_patience_counter":
|
| 3429 |
}
|
| 3430 |
},
|
| 3431 |
"TrainerControl": {
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 6750,
|
| 3 |
+
"best_metric": 0.8330850752448713,
|
| 4 |
+
"best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-6750",
|
| 5 |
+
"epoch": 42.654028436018955,
|
| 6 |
"eval_steps": 250,
|
| 7 |
+
"global_step": 9000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2916 |
},
|
| 2917 |
{
|
| 2918 |
"epoch": 41.58767772511848,
|
| 2919 |
+
"grad_norm": 1.0427478551864624,
|
| 2920 |
"learning_rate": 9.208530805687204e-05,
|
| 2921 |
+
"loss": 0.2537,
|
| 2922 |
"step": 8775
|
| 2923 |
},
|
| 2924 |
{
|
| 2925 |
"epoch": 41.70616113744076,
|
| 2926 |
+
"grad_norm": 2.969947338104248,
|
| 2927 |
"learning_rate": 9.149289099526066e-05,
|
| 2928 |
+
"loss": 0.2748,
|
| 2929 |
"step": 8800
|
| 2930 |
},
|
| 2931 |
{
|
| 2932 |
"epoch": 41.824644549763036,
|
| 2933 |
+
"grad_norm": 1.6928722858428955,
|
| 2934 |
"learning_rate": 9.090047393364928e-05,
|
| 2935 |
+
"loss": 0.2192,
|
| 2936 |
"step": 8825
|
| 2937 |
},
|
| 2938 |
{
|
| 2939 |
"epoch": 41.943127962085306,
|
| 2940 |
+
"grad_norm": 0.6375718116760254,
|
| 2941 |
"learning_rate": 9.03080568720379e-05,
|
| 2942 |
+
"loss": 0.2425,
|
| 2943 |
"step": 8850
|
| 2944 |
},
|
| 2945 |
{
|
| 2946 |
"epoch": 42.06161137440758,
|
| 2947 |
+
"grad_norm": 3.991424560546875,
|
| 2948 |
"learning_rate": 8.971563981042653e-05,
|
| 2949 |
+
"loss": 0.2885,
|
| 2950 |
"step": 8875
|
| 2951 |
},
|
| 2952 |
{
|
| 2953 |
"epoch": 42.18009478672986,
|
| 2954 |
+
"grad_norm": 1.3828190565109253,
|
| 2955 |
"learning_rate": 8.912322274881517e-05,
|
| 2956 |
+
"loss": 0.2549,
|
| 2957 |
"step": 8900
|
| 2958 |
},
|
| 2959 |
{
|
| 2960 |
"epoch": 42.29857819905213,
|
| 2961 |
+
"grad_norm": 1.6532574892044067,
|
| 2962 |
"learning_rate": 8.853080568720378e-05,
|
| 2963 |
+
"loss": 0.2439,
|
| 2964 |
"step": 8925
|
| 2965 |
},
|
| 2966 |
{
|
| 2967 |
"epoch": 42.41706161137441,
|
| 2968 |
+
"grad_norm": 0.6017269492149353,
|
| 2969 |
"learning_rate": 8.793838862559241e-05,
|
| 2970 |
+
"loss": 0.2385,
|
| 2971 |
"step": 8950
|
| 2972 |
},
|
| 2973 |
{
|
| 2974 |
"epoch": 42.535545023696685,
|
| 2975 |
+
"grad_norm": 5.455312252044678,
|
| 2976 |
"learning_rate": 8.734597156398103e-05,
|
| 2977 |
+
"loss": 0.2599,
|
| 2978 |
"step": 8975
|
| 2979 |
},
|
| 2980 |
{
|
| 2981 |
"epoch": 42.654028436018955,
|
| 2982 |
+
"grad_norm": 4.181074619293213,
|
| 2983 |
"learning_rate": 8.675355450236965e-05,
|
| 2984 |
+
"loss": 0.2277,
|
| 2985 |
"step": 9000
|
| 2986 |
},
|
| 2987 |
{
|
| 2988 |
"epoch": 42.654028436018955,
|
| 2989 |
+
"eval_dice": 0.8303639648030626,
|
| 2990 |
+
"eval_iou": 0.7502915429049051,
|
| 2991 |
+
"eval_loss": 0.2971900999546051,
|
| 2992 |
+
"eval_precision": 0.8819893121641817,
|
| 2993 |
+
"eval_recall": 0.8298137859517958,
|
| 2994 |
+
"eval_runtime": 4.0258,
|
| 2995 |
+
"eval_samples_per_second": 104.327,
|
| 2996 |
+
"eval_specificity": 0.990112645359611,
|
| 2997 |
+
"eval_steps_per_second": 26.082,
|
| 2998 |
"step": 9000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2999 |
}
|
| 3000 |
],
|
| 3001 |
"logging_steps": 25,
|
|
|
|
| 3010 |
"early_stopping_threshold": 0.0
|
| 3011 |
},
|
| 3012 |
"attributes": {
|
| 3013 |
+
"early_stopping_patience_counter": 3
|
| 3014 |
}
|
| 3015 |
},
|
| 3016 |
"TrainerControl": {
|